Scope of the Workshop


The overriding goal is not only to identify key but unsolved problems and expose the current state-of-the-art, but also to broaden the field and the community. Since plant phenotyping is an important aspect of agriculture and will support the sustainability of our planet and its inhabitants, having new vision scientists enter this field is more crucial than ever. 
We welcome submissions that propose interesting computer vision solutions, but also submissions that introduce challenging computer vision problems in plant phenotyping, accompanied with benchmark datasets and suitable performance evaluation methods.

Specific topics of interest include, but are not limited to, the following:

  • advances in segmentation, tracking, detection, reconstruction and identification methods that address unsolved plant phenotyping scenarios
  • open source implementation, comparison and discussion of existing methods and annotation tools
  • image data sets defining plant phenotyping challenges, complete with annotations if appropriate, accompanied with benchmark methods if possible, and suitable evaluation methods

Associated with the workshop are two computer vision challenges: a) the 2nd "Plant Leaf Segmentation Challenge" and b) the Leaf Counting Challenge:

We are looking forward to practical and inspiring leaf segmentation and counting solutions for automated plant phenotyping applications!

We also welcome submissions that use the provided data to support and develop annotation tools valuable for the community. For example, using leaf centers of the counting challenge, to evaluate and develop an interactive leaf segmentation tool

Phidas logo


EU and FP7 Logos




Some example images from data set